# US 2023/0069314 A1 · Dynamic video analytics rules based on human conversation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2023/0069314 A1
- Document ID: US20230069314A1
- Status: Published application
- Kind: A1
- Application number: 17/446,627
- Filed: 2021-09-01
- Published: 2023-03-02
- Earliest claimed: 2021-09-01
- Assignees: Motorola Solutions, Inc.
- Applicants: Motorola Solutions, Inc.
- Inventors: HAZIQ IQRAM BIN MOHAMMED SHAFRI; SEOW HONG CHAN; CHUNG YONG CHONG; CHOON HONG WONG
- Web page: https://patentgrep.com/patent/US20230069314A1

## CPC

- G08B 13/19613: {Recognition of a predetermined image pattern or behaviour pattern indicating theft or intrusion}
- H04N 7/18: Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- G06F 3/167: {Audio in a user interface, e.g. using voice commands for navigating, audio feedback}
- G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking
- G06Q 10/0633: Workflow analysis
- G06Q 10/0635: Risk analysis of enterprise or organisation activities
- G06Q 10/103: {Workflow collaboration or project management}
- G06Q 50/26: Government or public services (business processes related to the transportation industry G06Q50/40)
- G06V 20/62: Text, e.g. of license plates, overlay texts or captions on TV images
- G06V 40/172: {Classification, e.g. identification}
- G06F 40/295: Named entity recognition
- G06F 40/30: Semantic analysis
- G10L 15/26: Speech to text systems (G10L15/08 takes precedence)
- G08B: SIGNALLING SYSTEMS, e.g. PERSONAL CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G10L: SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING

## Abstract

At least one detected natural language phrase in audio describes at least one expected future object activity in a definable physical or geographic region. For each of one or more potential video analytic rules that are derivable from the at least one natural language phrase, whether compatibility with corresponding workflow requirements of an entity exists may be determined, such that one, some or all of the one or more potential video analytic rules are confirmed as one or more workflow-compatible video analytic rules. The one or more workflow-compatible video analytic rules are implemented within a video security system for respective one or more periods of time. For each of the implemented video analytic rules, a notification may be generated: when a rule violation of the respective video analytic rule triggers an event; or following expiry of the respective period of time of the one or more periods of time.

## Claims

### Claim 1

A computer-implemented method comprising:
detecting at least one natural language phrase in audio, wherein the at least one natural language phrase describes at least one expected future object activity in a definable physical or geographic region;
for each of one or more potential video analytic rules that are derivable from the at least one natural language phrase, determining whether compatibility with corresponding workflow requirements of an entity exists such that one, some or all of the one or more potential video analytic rules are confirmed as one or more workflow-compatible video analytic rules;
implementing the one or more workflow-compatible video analytic rules within a video security system for respective one or more periods of time; and
for each of the implemented video analytic rules, generating a notification:
when a rule violation of the respective video analytic rule triggers an event; or
following expiry of the respective period of time of the one or more periods of time.

### Claim 2 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein the notification provides evidence that is either confirming or contradicting in relation to whether the future object activity actually transpired.

### Claim 3 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein the one or more workflow-compatible video analytic rules are applied to live video accessible at one or more video cameras forming a part of the video security system.

### Claim 4 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein the event is at least one of an unusual activity event and a detection of unusual motion of an object present at one or more of a sensitive location and a sensitive time.

### Claim 5 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein:
the notification provides evidence that is contradicting in relation to whether the future object activity actually transpired, and
the future object activity is a departure of an object from the definable physical or geographic region.

### Claim 6 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein:
the notification provides evidence that is contradicting in relation to whether the future object activity actually transpired, and
the future object activity is an arrival of an object into the definable physical or geographic region.

### Claim 7 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein the audio is received via a microphone located remote from the definable physical or geographic region.

### Claim 8 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein the implementing of the one or more workflow-compatible video analytic rules within the video security system includes adding at least one entry to a watch list for either facial recognition alerting or license plate recognition alerting.

### Claim 9 (depends on 1)

The computer-implemented method as claimed in claim 1 wherein the rule violation occurs based on a confidence score being exceeded.

### Claim 10 (depends on 9)

The computer-implemented method as claimed in claim 9 further comprising:
checking secondary sources to determine an apparent inaccuracy of a statement made in the audio; and
increasing the confidence score based on the apparent inaccuracy of the statement.

### Claim 11

A computer-implemented method comprising:
detecting at least one natural language phrase in audio, wherein the at least one natural language phrase describes at least one expected future object activity in a definable physical or geographic region;
determining that an at least one video analytic rule, derivable from the at least one natural language phrase, cannot yet be implemented due to ambiguous information or due to missing information needed to satisfy corresponding workflow requirements of an entity;
generating a question expected to elicit an answer from which either the missing information will be obtained or the ambiguous information will be clarified;
perceptibly providing the question to a person via at least one of: displaying the question on a screen, and emitting the question audibly via a speaker; and
once the missing information is obtained or the ambiguous information is clarified, implementing the at least one video analytic rule within a video security system for a respective at least one period of time.

### Claim 12 (depends on 11)

The computer-implemented method of claim 11 further comprising:
detecting an additional natural language phrase in additional audio;
determining that the additional natural language phrase is the answer; and
deriving the missing information from the answer.

### Claim 13 (depends on 11)

The computer-implemented method as claimed in claim 11 wherein the implementing of the at least one video analytic rule includes applying the at least one video analytic rule to live video accessible at one or more video cameras forming a part of the video security system.

### Claim 14 (depends on 11)

The computer-implemented method as claimed in claim 11 wherein the audio is received via a microphone located remote from the definable physical or geographic region.

### Claim 15 (depends on 11)

The computer-implemented method as claimed in claim 11 wherein the implementing of the at least one analytic rule within the video security system includes adding at least one entry to a watch list for either facial recognition alerting or license plate recognition alerting.

### Claim 16

A security ecosystem comprising:
a microphone configured to receive audio;
at least one processor in communication with the microphone, and the at least one processor configured to:
detect at least one natural language phrase in the audio, wherein the at least one natural language phrase describes at least one expected future object activity in a definable physical or geographic region; and
for each of one or more potential video analytic rules that are derivable from the at least one natural language phrase, determine whether compatibility with corresponding workflow requirements of an entity exists such that one, some or all of the one or more potential video analytic rules are confirmed as one or more workflow-compatible video analytic rules; and
a video security system configured to:
implement the one or more workflow-compatible video analytic rules for respective one or more periods of time; and
for each of the implemented video analytic rules, generate a notification:
when a rule violation of the respective video analytic rule triggers an event; or
following expiry of the respective period of time of the one or more periods of time.
